Bivariate data ✔️✔️Data that involve two variables
Data ✔️✔️Information that has been collected
Discrete data ✔️✔️Data that can only take certain numerical values in a given range, e.g. Shoe sizes
Hypothesis ✔️✔️An assumption made as the starting point of an investigation. It should be a
statement.
Qualitative data ✔️✔️Observations that do not have numerical values and must be described in
words, e.g. Colour
Quantitative data ✔️✔️Observations that can take numerical values; that can be measured and given
as a number
Variable ✔️✔️A quantity that can have different values
Continuous data ✔️✔️Data that can take any value on a continuous scale, e.g. time; usually rounded
Census ✔️✔️Information about every member of the population
Population ✔️✔️Everybody or everything that could be involved in the investigation, e.g. Members of
a school
Random sample ✔️✔️The sample in which the people or items are chosen without making a
conscious decision. Each person or item has an equal chance of being selected
, Sample data ✔️✔️Information about part of the population
Sampling frame ✔️✔️A list of all the people or items in the population, e.g. a register of members of
the school
Sampling units ✔️✔️All the people or things in the population
Advantages of a census ✔️✔️Unbiased
Takes the whole population into account
- Accurate
Disadvantages of a sample ✔️✔️May be biased
Not completely representative
Disadvantages of a census ✔️✔️Expensive
Time consuming
Lots of data to handle
- Difficult to ensure the whole population is being used
Advantages of a sample ✔️✔️Cheaper
Less time consuming
Easy to manage
Simple random sampling ✔️✔️1) Number each item on the sampling frame
2) Obtain the required number of random numbers from a generator, table etc.
3) Select the items with these numbers
Stratified sampling ✔️✔️A sample when a population can be divided into strata (sub-populations),
each represented fairly, with items randomly selected within each stratum.